Update README.md

README.md

@@ -7,7 +7,7 @@ base_model:
 
 ## Model Details
 
-This awq model is an int4 model with group_size 32 and symmetric quantization of [SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview) generated by [intel/auto-round](https://github.com/intel/auto-round). 
+This awq model is an int4 model with group_size 32 and symmetric quantization of [PowerInfer/SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview) generated by [intel/auto-round](https://github.com/intel/auto-round). 
 
 ## How To Use
 ### Requirements
@@ -111,11 +111,10 @@ text="How many r in strawberry."
 
 ### Generate the model
 
-Here is the sample command to generate the model. For symmetric quantization, we found overflow/NAN will occur for some backends, so better fallback some layers. auto_round requires version >0.4.1
-
+Here is the sample command to generate the model.
 ```bash
 auto-round \
---model  QSmallThinker-3B-Preview \
+--model  PowerInfer/SmallThinker-3B-Preview \
 --device 0 \
 --group_size 32 \
 --bits 4 \